16
Models Available
$0.050
Cheapest Input / 1M
164K
Largest Context
What is Replicate?
Replicate is an AI model provider offering 16 large language models for developers. Their cheapest model starts at $0.050 per 1M input tokens, and their largest context window reaches 164K. Replicate provides 16 AI models accessible via API.
Replicate Strengths
All Replicate Models
| Model | Input $/1M | Output $/1M | Context | Max Output | Released |
|---|---|---|---|---|---|
| Meta/Llama 2 7b | $0.050 | $0.25 | 4K | 4,096 | — |
| Meta/Llama 2 7b Chat | $0.050 | $0.25 | 4K | 4,096 | — |
| Meta/Llama 3 8b | $0.050 | $0.25 | 8K | 8,086 | — |
| Meta/Llama 3 8b Instruct | $0.050 | $0.25 | 8K | 8,086 | — |
| Mistralai/Mistral 7b Instruct V0.2 | $0.050 | $0.25 | 4K | 4,096 | — |
| Mistralai/Mistral 7b V0.1 | $0.050 | $0.25 | 4K | 4,096 | — |
| Meta/Llama 2 13b | $0.10 | $0.50 | 4K | 4,096 | — |
| Meta/Llama 2 13b Chat | $0.10 | $0.50 | 4K | 4,096 | — |
| Mistralai/Mixtral 8x7b Instruct V0.1 | $0.30 | $1.00 | 4K | 4,096 | — |
| Meta/Llama 2 70b | $0.65 | $2.75 | 4K | 4,096 | — |
| Meta/Llama 2 70b Chat | $0.65 | $2.75 | 4K | 4,096 | — |
| Meta/Llama 3 70b | $0.65 | $2.75 | 8K | 8,192 | — |
| Meta/Llama 3 70b Instruct | $0.65 | $2.75 | 8K | 8,192 | — |
| Deepseek Ai/Deepseek V3.1 | $0.67 | $2.02 | 164K | 163,840 | — |
| Deepseek Ai/Deepseek | $1.45 | $1.45 | 66K | 8,192 | — |
| Deepseek Ai/Deepseek R1 | $3.75 | $10.00 | 66K | 8,192 | — |
Model Details
Meta/Llama 2 7b
Meta/Llama 2 7b is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.0500/1M input tokens, $0.2500/1M output tokens.
Meta/Llama 2 7b Chat
Meta/Llama 2 7b Chat is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.0500/1M input tokens, $0.2500/1M output tokens.
Meta/Llama 3 8b
Meta/Llama 3 8b is available via Replicate with a 8K context window and up to 8,086 output tokens. Pricing: $0.0500/1M input tokens, $0.2500/1M output tokens.
Meta/Llama 3 8b Instruct
Meta/Llama 3 8b Instruct is available via Replicate with a 8K context window and up to 8,086 output tokens. Pricing: $0.0500/1M input tokens, $0.2500/1M output tokens.
Mistralai/Mistral 7b Instruct V0.2
Mistralai/Mistral 7b Instruct V0.2 is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.0500/1M input tokens, $0.2500/1M output tokens.
Mistralai/Mistral 7b V0.1
Mistralai/Mistral 7b V0.1 is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.0500/1M input tokens, $0.2500/1M output tokens.
Meta/Llama 2 13b
Meta/Llama 2 13b is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.1000/1M input tokens, $0.5000/1M output tokens.
Meta/Llama 2 13b Chat
Meta/Llama 2 13b Chat is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.1000/1M input tokens, $0.5000/1M output tokens.
Mistralai/Mixtral 8x7b Instruct V0.1
Mistralai/Mixtral 8x7b Instruct V0.1 is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.3000/1M input tokens, $1.00/1M output tokens.
Meta/Llama 2 70b
Meta/Llama 2 70b is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.6500/1M input tokens, $2.75/1M output tokens.
Meta/Llama 2 70b Chat
Meta/Llama 2 70b Chat is available via Replicate with a 4K context window and up to 4,096 output tokens. Pricing: $0.6500/1M input tokens, $2.75/1M output tokens.
Meta/Llama 3 70b
Meta/Llama 3 70b is available via Replicate with a 8K context window and up to 8,192 output tokens. Pricing: $0.6500/1M input tokens, $2.75/1M output tokens.
Meta/Llama 3 70b Instruct
Meta/Llama 3 70b Instruct is available via Replicate with a 8K context window and up to 8,192 output tokens. Pricing: $0.6500/1M input tokens, $2.75/1M output tokens.
Deepseek Ai/Deepseek V3.1
Deepseek Ai/Deepseek V3.1 is available via Replicate with a 164K context window and up to 163,840 output tokens. Pricing: $0.6720/1M input tokens, $2.02/1M output tokens.
Deepseek Ai/Deepseek
Deepseek Ai/Deepseek is available via Replicate with a 66K context window and up to 8,192 output tokens. Pricing: $1.45/1M input tokens, $1.45/1M output tokens.
Deepseek Ai/Deepseek R1
Deepseek Ai/Deepseek R1 is available via Replicate with a 66K context window and up to 8,192 output tokens. Pricing: $3.75/1M input tokens, $10.00/1M output tokens.
Compare Replicate model pricing
Use our pricing calculator to find the cheapest Replicate model for your workload.